© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64874
    Prev
    Next
    INDEX
    Explanations

    list items and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haj
    -0.07
    æģª
    -0.07
    erbe
    -0.07
    aml
    -0.06
    &M
    -0.06
     latter
    -0.06
     (\
    -0.06
    hart
    -0.06
    wen
    -0.06
    OptionsMenu
    -0.06
    POSITIVE LOGITS
    ?,?,
    0.08
     quoi
    0.08
    ?,?,?,?,
    0.07
    _states
    0.07
    ","","
    0.07
    âĢ¦,
    0.07
    ÙĬع
    0.07
    ä¾ĽåºĶ产åĵģ
    0.07
    Invoker
    0.07
    å¼ı设计
    0.07
    Activations Density 0.017%

    No Known Activations